Comprehensive agricultural machinery scheduling method, device and equipment

Through the snake optimization algorithm, the demand and utilization rate of agricultural machinery are processed, the target allocation matrix is ​​obtained, and the problem of local optimal solutions in large-scale agricultural machinery scheduling is solved, and the accuracy and utilization rate of agricultural machinery scheduling is improved.

CN119005630APending Publication Date: 2024-11-22SHIHEZI UNIVERSITY
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411234434.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-03
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The prior art is prone to falling into local optimal solutions in large-scale agricultural machinery scheduling, and the algorithm solution complexity is high, resulting in low optimization accuracy of agricultural machinery scheduling and increased energy consumption costs.

Method used

Using the snake optimization algorithm, by obtaining the demand and utilization rate of agricultural machinery in each target area, snake optimization process is carried out to obtain the target allocation matrix, determine the allocation amount of agricultural machinery of various categories, avoid local optimal solutions and improve the utilization rate of agricultural machinery.

Benefits of technology

It effectively avoids local optimal solutions, improves the accuracy and utilization rate of agricultural machinery scheduling, and realizes the reasonable allocation and scheduling of agricultural machinery.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119005630A_ABST
    Figure CN119005630A_ABST
Patent Text Reader

Abstract

The invention discloses a comprehensive agricultural machinery scheduling method, device and equipment, and belongs to the technical field of agricultural machinery scheduling, and the method comprises the steps: receiving the demands of each target region for various types of agricultural machinery from clients corresponding to each target region; based on the utilization rate of each target area for each type of agricultural machinery and the agricultural machinery shortage condition of each target area, snake optimization processing is carried out to acquire a target distribution matrix, and the target distribution matrix comprises distribution vectors corresponding to each target area; the distribution vector corresponding to any target area is used for indicating the weight of each type of agricultural machinery corresponding to the target area; and according to the demand quantity of each target area for each type of agricultural machinery and the target distribution matrix, determining the distribution quantity of each target area for each type of agricultural machinery. The method can meet the requirements of each target area for various types of agricultural machinery, improves the comprehensive utilization rate of the agricultural machinery, and achieves the reasonable scheduling of the agricultural machinery.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of agricultural machinery scheduling, and in particular relates to a comprehensive agricultural machinery scheduling method, device and equipment. Background Art

[0002] Agricultural machinery scheduling refers to the reasonable arrangement and scheduling of various agricultural machinery and equipment according to the demand for agricultural production and the allocation of resources. Its core goal is to meet the reasonable and reliable requirements of agricultural production for agricultural machinery scheduling, optimize and promote the optimization of various agricultural machinery scheduling, so as to maximize agricultural production efficiency and resource utilization. Therefore, how to optimize agricultural machinery scheduling has become a key issue that needs to be solved urgently.

[0003] In related technologies, swarm intelligence algorithms are usually used for scheduling optimization. For example, when the ant colony algorithm is applied to agricultural machinery scheduling problems, the ant colony algorithm includes steps such as initialization, pheromone update, and update of global optimality. It comprehensively considers factors such as supply and demand matching and operating capacity, and conducts large-scale global search and subtle local optimization in the search space, thereby determining the agricultural machinery scheduling decision for agricultural production.

[0004] However, for large-scale agricultural machinery scheduling problems, the use of ant colony algorithm to optimize energy scheduling is prone to fall into local optimality, and its algorithm has high solution complexity and slow convergence speed, which will lead to low accuracy of agricultural machinery scheduling optimization and increased energy consumption costs. Summary of the invention

[0005] In order to solve the above technical problems, the present invention proposes a comprehensive agricultural machinery scheduling method, device and equipment to solve the problems existing in the above-mentioned prior art.

[0006] To achieve the above object, the present invention provides a comprehensive agricultural machinery scheduling method, comprising:

[0007] Obtain the demand for agricultural machinery in each target area, and obtain the agricultural machinery utilization rate and agricultural machinery shortage vector in each target area;

[0008] Performing snake optimization processing on the agricultural machinery utilization rate and agricultural machinery shortage situation vectors to obtain a target allocation matrix;

[0009] The allocation quantity of each target area for each type of machine model is determined based on the demand for agricultural machinery in each target area and the target allocation matrix.

[0010] Preferably, the process of performing snake optimization processing on the agricultural machinery utilization rate and the agricultural machinery shortage to obtain the target allocation matrix includes:

[0011] Get the initialization parameters and the initialization position matrix of the snake;

[0012] Based on the agricultural machinery utilization rate and agricultural machinery shortage situation of each target area, the initialization position matrix of the snake is iterated T times to obtain the position matrix of each snake after the Tth iteration;

[0013] The target allocation matrix is ​​obtained based on the position matrix of each snake after the Tth iteration.

[0014] Preferably, the process of obtaining the position matrix of each snake after the Tth iteration further includes:

[0015] Determine the target position matrix after the t-th iteration based on the position matrices of each snake after the t-th iteration;

[0016] According to the target position matrix after the t-th iteration, iteratively process the position matrix of each snake after the t-th iteration to obtain the position matrix of each snake after the t+1-th iteration;

[0017] Among them, {t|t=0,1,2,…,T-1}.

[0018] Preferably, the process of determining the target position matrix after the t-th iteration based on the position matrices of each snake after the t-th iteration includes:

[0019] Obtaining the benefit value corresponding to the snake position matrix after the tth iteration for the agricultural machinery utilization rate and agricultural machinery shortage situation vector;

[0020] Determining the target allocation matrix after the t-th iteration based on the benefit value and the snake position matrix after the t-th iteration;

[0021] The target allocation matrix includes allocation vectors corresponding to each of the target areas, and the allocation vector corresponding to any target area is used to indicate the weight of each category of agricultural machinery corresponding to the target area;

[0022] The initialization position matrix of the snake contains M×N elements, where M is the number of the target areas, and N is the number of categories of agricultural machinery, and both M and N are integers greater than 1.

[0023] Preferably, the process of iteratively processing the position matrices of each snake after the t-th iteration according to the target position matrix after the t-th iteration to obtain the position matrices of each snake after the t+1-th iteration includes:

[0024] Obtaining a control variable corresponding to the t-th iteration, wherein the control variable corresponding to the t-th iteration is used to control the influence of food and temperature on each snake in the next step, and is used to control the fighting and mating of each snake;

[0025] According to the control variables corresponding to the t-th iteration and the target position matrix after the t-th iteration, the position matrix of each snake after the t-th iteration is iteratively processed to obtain the position matrix of each snake after the t+1-th iteration.

[0026] Preferably, the process of obtaining the control variable corresponding to the t-th iteration includes:

[0027] Obtaining a first preset parameter;

[0028] Obtaining a control variable corresponding to the tth iteration according to the first preset parameter and the current iteration number t;

[0029] The expression of the control variable corresponding to the t-th iteration is:

[0030]

[0031] Among them, Q and Temp are control variables corresponding to the t-th iteration, and c1 is the first preset parameter.

[0032] Preferably, at the t+1 iteration, if Q<0.25, the position matrices of the i-th male snake and the female snake satisfy:

[0033]

[0034] Among them, X i,m X is the individual position of male snake; i,f X is the individual position of female snake; rand,m is the position of a randomly selected male snake; X rand,f is the position of a randomly selected female snake; rand is a random number between [0, 1]; f rand,m X is the position of the randomly selected male snake individual rand,m Return value; f i,m X is the position of the male snake i,m Return value; f rand,f X is the position of the randomly selected female snake rand,f Return value; f i,f X is the position of the female snake i,f Profit value; c2 is the second preset parameter; X max is the upper boundary of the snake in the position matrix; X min is the lower boundary of the snake in the position matrix;

[0035] At the t+1 iteration, if Q>0.25 and Temp>0.6, the snake position matrix satisfies:

[0036] X i,j (t+1)=X food±c3×Temp×rand×(X food -X i,j (t))

[0037] Among them, X i,j is the individual position; X food is the current optimal benefit; c3 is the third preset parameter;

[0038] At the t+1 iteration, if Q>0.25 and Temp<0.6, the snake will randomly enter the fighting state or the mating state. When entering the fighting state, the snake's position matrix satisfies:

[0039]

[0040] Among them, X i,m is the position of the ith male snake; X best,f X is the best position for female snakes; i,f is the position of the ith female individual; X best,m is the best position for male individuals; f best,f is the best benefit value among female snakes; f best,m is the best benefit value among male snakes; f i is the current revenue value;

[0041] When entering the mating state, the snake's position matrix satisfies:

[0042]

[0043] Among them, X i,m is the position of the ith male snake; X i,f is the position of the ith female snake; f i,m is the profit value of the ith male individual position; f i,f is the profit value of the i-th female individual position.

[0044] Preferably, the process of determining the allocation amount of each target area for each type of machine model based on the agricultural machinery demand of each target area and the target allocation matrix includes:

[0045] Determine the weight ratio of each target area to each category of agricultural machinery according to the target allocation matrix;

[0046] The allocation quantity of each target area for each category of agricultural machinery is determined according to the weight ratio of each target area to each category of agricultural machinery and the demand of each target area for each category of agricultural machinery.

[0047] To achieve the above object, the present invention also provides a comprehensive agricultural machinery scheduling device, comprising:

[0048] A receiving module, used for receiving the demand for each type of agricultural machinery in each target area from the clients corresponding to each target area;

[0049] A processing module, used for performing snake optimization processing based on the utilization rate of each target area for each type of agricultural machinery and the shortage of agricultural machinery in each target area to obtain a target allocation matrix;

[0050] The determination module is used to determine the allocation quantity of each target area for each category of agricultural machinery according to the demand quantity of each target area for each category of agricultural machinery and the target allocation matrix.

[0051] To achieve the above objectives, the present invention also provides a comprehensive agricultural machinery scheduling device, including: a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements a comprehensive agricultural machinery scheduling method when executing the program.

[0052] Compared with the prior art, the present invention has the following advantages and technical effects:

[0053] The comprehensive agricultural machinery scheduling method, device and equipment provided by the embodiment of the present invention receive the demand for various types of agricultural machinery in each target area from the client corresponding to each target area; perform snake optimization processing based on the utilization rate of each target area for each type of agricultural machinery and the shortage of agricultural machinery in each target area to obtain a target allocation matrix, wherein the target matrix includes allocation vectors corresponding to each target area, and the allocation vector corresponding to any target area is used to indicate the weight of each type of agricultural machinery corresponding to the target area; according to the demand for each type of agricultural machinery in each target area and the target allocation matrix, determine the allocation of each type of agricultural machinery in each target area. In view of the problem that it is difficult to achieve reasonable scheduling of comprehensive agricultural machinery due to deep coupling or conflict in comprehensive agricultural machinery scheduling, through snake optimization processing, when facing large-scale agricultural machinery scheduling problems, the solution of agricultural machinery scheduling is realized, which can avoid falling into a local optimal solution, can meet the demand for each type of agricultural machinery in each target area, improve the comprehensive utilization rate of agricultural machinery, and achieve reasonable scheduling of agricultural machinery. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0055] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present invention;

[0056] Figure 2 A schematic diagram of a flow chart of a comprehensive agricultural machinery scheduling method provided by an embodiment of the present invention;

[0057] Figure 3 A schematic diagram of a process for obtaining a target allocation matrix provided by an embodiment of the present invention;

[0058] Figure 4 A schematic diagram of an iterative process flow provided by an embodiment of the present invention;

[0059] Figure 5 A schematic diagram of a process for obtaining a target allocation matrix provided by an embodiment of the present invention;

[0060] Figure 6 A schematic diagram for comparing the agricultural machinery scheduling method provided by an embodiment of the present invention;

[0061] Figure 7 A schematic diagram of the structure of a comprehensive agricultural machinery dispatching device provided by an embodiment of the present invention;

[0062] Figure 8 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0063] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0064] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0065] Embodiment 1

[0066] This embodiment provides a comprehensive agricultural machinery scheduling method, including:

[0067] In a first aspect, the present invention provides a comprehensive agricultural machinery scheduling method, comprising:

[0068] Receive the demand for each type of agricultural machinery in each target area from the clients corresponding to each target area;

[0069] Based on the utilization rate of each target area for each type of agricultural machinery and the shortage of agricultural machinery in each target area, a snake optimization process is performed to obtain a target allocation matrix, wherein the target allocation matrix includes allocation vectors corresponding to each target area, and the allocation vector corresponding to any target area is used to indicate the weight of each type of agricultural machinery corresponding to the target area;

[0070] The allocation quantity of each target area for each type of agricultural machinery is determined according to the demand quantity of each target area for each type of agricultural machinery and the target allocation matrix.

[0071] In a possible implementation, the snake optimization process is performed based on the utilization rate of each target area for each type of agricultural machinery and the shortage of agricultural machinery in each target area to obtain a target allocation matrix, including:

[0072] Obtain initialization parameters, including the maximum number of iterations T, the number of snakes S (snakes are divided into male snakes and female snakes, the number of which is S / 2 respectively), and the initialization position matrix of each snake, and any position matrix contains M×N elements, where M is the number of target areas and N is the number of agricultural machinery categories. Both M and N are integers greater than 1;

[0073] According to the utilization rate of each target area for each type of agricultural machinery and the shortage of agricultural machinery in each target area, the initialization position matrix of each snake is iterated T times to obtain the position matrix of each snake after the Tth iteration;

[0074] The target allocation matrix is ​​obtained according to the position matrix of each snake after the Tth iteration.

[0075] In a possible implementation, the initialization position matrix of each snake is iterated T times according to the utilization rate of each target area for each category of agricultural machinery and the shortage of agricultural machinery in each target area, to obtain the position matrix of each snake after the Tth iteration, including:

[0076] Determine the target position matrix after the t-th iteration in the position matrix of each of the snakes after the t-th iteration according to the agricultural machinery utilization matrix and the shortage vector;

[0077] According to the target position matrix after the t-th iteration, iteratively process the position matrix of each snake after the t-th iteration to obtain the position matrix of each snake after the t+1-th iteration;

[0078] Wherein, {t|t=0,1,2,…,T-1}, the position matrix of each snake after the 0th iteration is the initialization position matrix of the position matrix of each snake;

[0079] The agricultural machinery utilization rate matrix includes M×N elements, and the element in the mth row and nth column of the agricultural machinery utilization rate matrix is ​​used to indicate the utilization rate of the mth target area for the nth category of agricultural machinery, wherein m is greater than or equal to 1 and less than or equal to M, and n is greater than or equal to 1 and less than or equal to N;

[0080] The agricultural machinery shortage vector contains M elements, and any i-th element in the shortage vector is used to indicate the agricultural machinery shortage situation in the i-th target area, where i is greater than or equal to 1 and less than or equal to M.

[0081] In a possible implementation, determining the target position matrix after the t-th iteration in the position matrix of each snake after the t-th iteration according to the agricultural machinery utilization matrix and the shortage vector includes:

[0082] According to the agricultural machinery utilization rate matrix and the agricultural machinery shortage situation vector, obtaining the benefit value corresponding to the position matrix of each snake after the tth iteration;

[0083] According to the benefit values, the target position matrix after the t-th iteration is determined in the position matrix of each snake after the t-th iteration.

[0084] In a possible implementation, the position matrix of each snake after the t-th iteration according to the target position matrix after the i-th iteration includes:

[0085] The control variable corresponding to the t-th iteration is obtained, and the control variable corresponding to the t-th iteration is used to control the influence of food and temperature on each of the snakes in the next step, and to control the fighting and mating of each of the snakes.

[0086] According to the control variables corresponding to the t-th iteration and the target position matrix after the t-th iteration, the position matrix of each snake after the t-th iteration is iteratively processed to obtain the position matrix of each snake after the t+1-th iteration.

[0087] In a possible implementation manner, obtaining the control variable corresponding to the t-th iteration includes:

[0088] Obtaining a first preset parameter;

[0089] Obtaining a control variable corresponding to the tth iteration according to the first preset parameter and the current iteration number t;

[0090] in, The Q and Temp are control variables corresponding to the t-th iteration, and the c1 is a first preset parameter.

[0091] In one possible implementation, at the t+1 iteration, if Q<0.25, the position matrices of the i-th male snake and the female snake satisfy:

[0092]

[0093] Among them, X i,m X is the individual position of male snake; i,f X is the individual position of female snake; rand,m is the position of a randomly selected male snake; X rand,f is the position of a randomly selected female snake; rand is a random number between [0, 1]; f rand,mX is the position of the randomly selected male snake individual rand,m Return value; f i,m X is the position of the male snake i,m Return value; f rand,f X is the position of the randomly selected female snake rand,f Return value; f i,f X is the position of the female snake i,f Profit value; c2 is the second preset parameter. max is the upper boundary of the snake in the position matrix; X min is the lower boundary of the snake in the position matrix.

[0094] At the t+1 iteration, if Q>0.25 and Temp>0.6, the snake's position matrix satisfies:

[0095] X i,j (t+1)=X food ±c3×Temp×rand×(X food -X i,j (t))

[0096] Among them, X i,j is the individual position; X food is the current optimal profit; c3 is the third preset parameter.

[0097] At the t+1 iteration, if Q>0.25 and Temp<0.6, the snake will randomly enter the fighting state or the mating state. When entering the fighting state, the snake's position matrix satisfies:

[0098]

[0099] Among them, X i,m is the position of the ith male snake; X best,f X is the best position for female snakes; i,f is the position of the ith female individual; X best,m is the best position for male individuals; f best,f is the best benefit value among female snakes; f best,m is the best benefit value among male snakes; f i is the current revenue value.

[0100] When entering the mating state, the snake's position matrix satisfies:

[0101]

[0102] Among them, X i,m is the position of the ith male snake; X i,f is the position of the ith female snake; f i,mis the profit value of the ith male individual position; f i,f is the profit value of the ith female individual position.

[0103] In a possible implementation, determining the allocation amount of each target area for each type of agricultural machinery according to the demand amount of each target area for each type of agricultural machinery and the target allocation matrix includes:

[0104] Determine the weight ratio of each target area to each category of agricultural machinery according to the target allocation matrix;

[0105] The allocation quantity of each target area for each category of agricultural machinery is determined according to the weight ratio of each target area to each category of agricultural machinery and the demand of each target area for each category of agricultural machinery.

[0106] In a second aspect, the present invention provides a comprehensive agricultural machinery scheduling device, comprising:

[0107] The receiving module is used to receive the demand for each type of agricultural machinery in each target area from the clients corresponding to each target area.

[0108] A processing module, used for performing snake optimization processing based on the utilization rate of each target area for each category of agricultural machinery and the shortage of agricultural machinery in each target area, and obtaining a target allocation matrix, wherein the target allocation matrix includes allocation vectors corresponding to each target area, and the allocation vector corresponding to any target area is used to indicate the weight of each category of agricultural machinery corresponding to the target area;

[0109] The determination module is used to determine the allocation quantity of each target area for each category of agricultural machinery according to the demand quantity of each target area for each category of agricultural machinery and the target allocation matrix.

[0110] In a possible implementation manner, the processing module is specifically applied to:

[0111] Obtain initialization parameters, including the maximum number of iterations T, the number of snakes S (snakes are divided into male snakes and female snakes, the number of which is S / 2 respectively), and the initialization position matrix of each snake, and any position matrix contains M×N elements, where M is the number of target areas and N is the number of agricultural machinery categories. Both M and N are integers greater than 1;

[0112] According to the utilization rate of each target area for each type of agricultural machinery and the shortage of agricultural machinery in each target area, the initialization position matrix of each snake is iterated T times to obtain the position matrix of each snake after the Tth iteration;

[0113] The target allocation matrix is ​​obtained according to the position matrix of each snake after the Tth iteration.

[0114] In a possible implementation manner, the processing module is specifically applied to:

[0115] Determine the target position matrix after the tth iteration in the position matrix of each of the snakes after the tth iteration according to the agricultural machinery utilization matrix and the shortage vector;

[0116] According to the target position matrix after the t-th iteration, iteratively process the position matrix of each snake after the t-th iteration to obtain the position matrix of each snake after the t+1-th iteration;

[0117] Wherein, {t|t=0,1,2,…,T-1}, the position matrix of each snake after the 0th iteration is the initialization position matrix of the position matrix of each snake;

[0118] The agricultural machinery utilization rate matrix includes M×N elements, and the element in the mth row and nth column of the agricultural machinery utilization rate matrix is ​​used to indicate the utilization rate of the mth target area for the nth category of agricultural machinery, wherein m is greater than or equal to 1 and less than or equal to M, and n is greater than or equal to 1 and less than or equal to N;

[0119] The agricultural machinery shortage vector contains M elements, and any i-th element in the shortage vector is used to indicate the agricultural machinery shortage situation in the i-th target area, where i is greater than or equal to 1 and less than or equal to M.

[0120] In a possible implementation manner, the processing module is specifically applied to:

[0121] The control variable corresponding to the t-th iteration is obtained, and the control variable corresponding to the t-th iteration is used to control the influence of food and temperature on each of the snakes in the next step, and to control the fighting and mating of each of the snakes.

[0122] According to the control variables corresponding to the t-th iteration and the target position matrix after the t-th iteration, the position matrix of each snake after the t-th iteration is iteratively processed to obtain the position matrix of each snake after the t+1-th iteration.

[0123] In a possible implementation manner, the processing module is specifically applied to:

[0124] Obtaining a first preset parameter;

[0125] Obtaining a control variable corresponding to the tth iteration according to the first preset parameter and the current iteration number t;

[0126] in, The Q and Temp are control variables corresponding to the t-th iteration, and the c1 is a first preset parameter.

[0127] In one possible implementation, at the t+1 iteration, if Q<0.25, the position matrices of the i-th male snake and the female snake satisfy:

[0128]

[0129] Among them, X i,m X is the individual position of male snake; i,f X is the individual position of female snake; rand,m is the position of a randomly selected male snake; X rand,f is the position of a randomly selected female snake; rand is a random number between [0, 1]; f rand,m X is the position of the randomly selected male snake individual rand,m Return value; f i,m X is the position of the male snake i,m Return value; f rand,f X is the position of the randomly selected female snake rand,f Return value; f i,f X is the position of the female snake i,f Profit value; c2 is the second preset parameter. max is the upper boundary of the snake in the position matrix; X min is the lower boundary of the snake in the position matrix.

[0130] At the t+1 iteration, if Q>0.25 and Temp>0.6, the snake position matrix satisfies:

[0131] X i,j (t+1)=X food ±c3×Temp×rand×(X food -X i,j (t))

[0132] Among them, X i,j is the individual position; X food is the current optimal profit; c3 is the third preset parameter.

[0133] At the t+1 iteration, if Q>0.25 and Temp<0.6, the snake will randomly enter the fighting state or the mating state. When entering the fighting state, the snake's position matrix satisfies:

[0134]

[0135] Among them, X i,m is the position of the ith male snake; X best,fX is the best position for female snakes; i,f is the position of the ith female individual; X best,m is the best position for male individuals; f best,f is the best benefit value among female snakes; f best,m is the best benefit value among male snakes; f i is the current revenue value.

[0136] When entering the mating state, the snake's position matrix satisfies:

[0137]

[0138] Among them, X i,m is the position of the ith male snake; X i,f is the position of the ith female snake; f i,m is the profit value of the ith male individual position; f i,f is the profit value of the i-th female individual position.

[0139] In a possible implementation manner, the determining module is specifically applied to:

[0140] Determine the weight ratio of each target area to each category of agricultural machinery according to the target allocation matrix;

[0141] The allocation quantity of each target area for each category of agricultural machinery is determined according to the weight ratio of each target area to each category of agricultural machinery and the demand of each target area for each category of agricultural machinery.

[0142] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the integrated agricultural machinery scheduling method as described in any one of the first aspects is implemented.

[0143] In a fourth aspect, the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the integrated agricultural machinery scheduling method as described in any one of the first aspects is implemented.

[0144] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, which, when executed by a processor, implements the comprehensive agricultural machinery scheduling method as described in any one of the first aspects.

[0145] Embodiment 2

[0146] This embodiment provides a comprehensive agricultural machinery scheduling method, including:

[0147] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present invention, such as Figure 1 As shown, including multiple farms ( Figure 1 Four farms are exemplified, namely the first farm, the second farm, the third farm and the fourth farm), each farm includes a corresponding client, namely the first client corresponding to the first farm, the second client corresponding to the second farm, the third client corresponding to the third farm, and the fourth client corresponding to the fourth farm.

[0148] Each client and server are connected via a wireless network. The client is a device that can access the Internet, such as a mobile phone, computer, tablet, smart watch, etc., and the server is a control host. Each client can send the corresponding farm's demand information for various types of agricultural machinery to the server, and then the server will realize the unified dispatch of various types of agricultural machinery based on the demand information of each farm, that is, determine the number of various types of agricultural machinery to be allocated to each farm. Figure 1 Based on the example application scenarios, the solution of the present invention is introduced in conjunction with the accompanying drawings.

[0149] Figure 2 A flow chart of a comprehensive agricultural machinery scheduling method provided by an embodiment of the present invention is shown in FIG. Figure 2 As shown, the method may include:

[0150] S21, receiving the demand for each type of agricultural machinery in each target area from the clients corresponding to each target area.

[0151] The execution subject of the embodiment of the present invention may be a host of an agricultural machinery dispatching center, which may be a server, a processor, etc., or a device integrating the functions of a server or a processor.

[0152] For target areas that need various types of agricultural machinery, the client corresponding to each target area can send the demand for each type of agricultural machinery in the corresponding target area to the host, and the demand can be the demand for a certain period of time. Among them, the target area is mainly a farm, and the target area needs the corresponding supply of agricultural machinery. The categories of agricultural machinery include trenchers, fertilizer applicators, pesticide applicators, seeders, film laying machines, harvesters and other different types of agricultural machinery.

[0153] The host can receive the demand for each category of agricultural machinery in each target area from the clients corresponding to each target area. For example, the target areas include farm agricultural machinery scheduling, farm B and farm C, and the categories of agricultural machinery include trenchers, fertilizer applicators, pesticide applicators, seeders, film laying machines, and harvesters. The host can receive the demand for each category of agricultural machinery from the farm agricultural machinery scheduling client. Similarly, the host can receive the demand for each category of agricultural machinery from farm B from the client corresponding to farm B. The period for the client to send the above demand can be half a day, one day, etc., which can be set according to actual needs.

[0154] S22, based on the utilization rate of each target area for each category of agricultural machinery and the shortage of agricultural machinery in each target area, snake optimization processing is performed to obtain a target allocation matrix, wherein the target allocation matrix includes allocation vectors corresponding to each target area, and the allocation vector corresponding to any target area is used to indicate the weight of each category of agricultural machinery corresponding to the target area.

[0155] The utilization rate of each type of agricultural machinery in each target area and the shortage of agricultural machinery in each target area can be received from the client corresponding to each target area. For example, the utilization rate of the seeder and the utilization rate of the pesticide applicator of the farm agricultural machinery scheduling, as well as the shortage of agricultural machinery in the farm agricultural machinery scheduling can be obtained from the client corresponding to the farm agricultural machinery scheduling. The shortage of agricultural machinery is used to indicate the degree of lack of agricultural machinery in the target area. Among them, the utilization rate of agricultural machinery in the target area and the shortage of agricultural machinery remain unchanged in a short period of time. Therefore, within a period of time, the client only needs to send the utilization rate of each type of agricultural machinery in the target area and the shortage of agricultural machinery once.

[0156] After obtaining the utilization rate of each target area for each type of agricultural machinery and the shortage of agricultural machinery, snake optimization processing can be performed based on the utilization rate of each target area for each type of agricultural machinery and the shortage of agricultural machinery in each target area to obtain the target allocation matrix. The number of columns in the target allocation matrix is ​​the number of target areas, and the number of rows is the number of agricultural machinery categories. The target allocation matrix can be used to indicate the weight of each type of agricultural machinery in the target area, that is, how to allocate each type of agricultural machinery.

[0157] S23, determining the allocation quantity of each target area for each type of agricultural machinery according to the demand quantity of each target area for each type of agricultural machinery and the target allocation matrix.

[0158] After obtaining the target allocation matrix, the allocation amount of each target area for each category of agricultural machinery can be calculated based on the weights of each category of agricultural machinery corresponding to each target area indicated in the target allocation matrix and the demand for each category of agricultural machinery in each target area.

[0159] For example, if there are sufficient agricultural machinery, the weights of a target area for seed drills, pesticide sprayers, and fertilizer sprayers are 0.5:0.2:0.3, and the demand for these types of agricultural machinery in the target area is 4, 2, and 2, respectively. Then, the weight is divided by the demand, and the demand for the agricultural machinery category corresponding to the minimum value is taken as the allocation of the agricultural machinery of this category, and then the allocation of other categories of agricultural machinery is obtained. For example, 0.5 / 4=0.125, 0.2 / 2=0.1, 0.3 / 2=0.15, and the minimum value is 0.1. Then the demand for pesticide sprayers is 2 as the allocation of pesticide sprayers in the target area, and then the allocation of other categories of agricultural machinery is determined in combination with the weight value.

[0160] For example, if the weights of the seed drill and the pesticide sprayer are 0.5:0.2, and the allocation of the pesticide sprayer is 2, then the allocation of the seed drill can be set to 5, and the allocation of a similar fertilizer sprayer can be set to 3. This can meet the needs of the target area for various types of agricultural machinery.

[0161] The comprehensive agricultural machinery scheduling method provided by the embodiment of the present invention receives the demand for each category of agricultural machinery in each target area from the client corresponding to each target area, and then performs snake optimization processing based on the utilization rate of each category of agricultural machinery in each target area and the shortage of agricultural machinery in the target area to obtain a target allocation matrix, wherein the target allocation matrix includes allocation vectors corresponding to each target area, and the allocation vector corresponding to any target area is used to indicate the weight of each category of agricultural machinery corresponding to the target area, and finally determines the allocation of each category of agricultural machinery in each target area according to the demand for each category of agricultural machinery in each target area and the target allocation matrix. In view of the fact that the comprehensive agricultural machinery scheduling has deep coupling or conflict, which makes it difficult to achieve the solution for the comprehensive agricultural machinery scheduling, through snake optimization processing, when facing large-scale agricultural machinery guidance problems, the solution of agricultural machinery scheduling is achieved, which can avoid falling into local optimality, can meet the demand for each category of agricultural machinery in each target area, improve the utilization rate of agricultural machinery, and achieve reasonable scheduling of agricultural machinery.

[0162] The comprehensive agricultural machinery scheduling method proposed by the present invention is further described in detail below with reference to the accompanying drawings.

[0163] Swarm intelligence algorithms can give full play to the advantages of clusters, such as self-organization, no central control, high robustness, flexibility and low consumption, and can still provide optimal solutions when facing large-scale complex problems. At the same time, they are widely used in practical problems such as function optimization, multi-objective optimization, solving integer constraints and mixed constraint optimization. The snake optimization algorithm is a kind of swarm intelligence algorithm, which can be applied to solving multi-objective complex models. It uses female and male snakes in the snake group for iterative search, and can evolve in different directions according to changes in temperature and food storage. This algorithm can well solve the problem that traditional algorithms are prone to fall into local optimal solutions.

[0164] In the regional comprehensive agricultural machinery intelligent scheduling, it is necessary to simultaneously meet the needs of multiple target areas for various types of agricultural machinery such as seed drills, pesticide applicators, and fertilizer applicators (involving the need to input a large number of parameters, scheduling multi-objective optimization, etc.), which happens to match the characteristics of the snake optimization algorithm in solving problems. Therefore, the snake optimization algorithm is applied to the regional comprehensive agricultural machinery intelligent scheduling solution to meet the needs of various target areas for various agricultural machinery and improve the utilization rate of agricultural machinery. Figure 3 This paper introduces the process of obtaining the target allocation matrix based on the snake optimization algorithm.

[0165] Figure 3 A schematic diagram of a flow chart of obtaining a target allocation matrix provided by an embodiment of the present invention is as follows: Figure 3 As shown, including:

[0166] S31, obtaining initialization parameters, the initialization parameters including the maximum number of iterations T, the number of snakes S (snakes are divided into male snakes and female snakes, the number of each accounts for S / 2) and the initialization position matrix of each snake.

[0167] Both T and S are natural numbers, that is, both T and S are integers greater than 1. The snake position matrix is ​​a two-dimensional matrix, and the elements in the matrix can be represented by floating-point numbers.

[0168] Each row of the snake position matrix includes M elements and each column includes N elements. M is the number of target areas and N is the number of agricultural machinery categories. Both M and N are positive integers. For example, if we want to assign three types of agricultural machinery, namely, planters, pesticide applicators and fertilizer applicators, to six target areas, the snake position matrix is ​​a matrix of 6 columns × 3 rows. Before iterative processing, the position matrix can be initialized to obtain the initialization matrix of each snake. For any snake, the sum of the N elements in each column of the initialization position matrix of the snake is 1, and each element in the initialization position matrix is ​​a number greater than 1 or equal to 0.

[0169] Each row of the position matrix corresponds to a category of agricultural machinery. For example, for the three categories of hidden agricultural machinery, namely, seed drill, pesticide applicator and fertilizer applicator, the first row corresponds to the seed drill, the second row corresponds to the pesticide applicator, and the third row corresponds to the fertilizer applicator. For different numbers of target areas, the number of columns of the position matrix is ​​different, and for different numbers of categories of agricultural machinery, the number of rows of the position matrix is ​​different, and the order of the categories of agricultural machinery corresponding to each row of the position matrix can be set as needed. For example, the first row can correspond to the fertilizer applicator, the second row to the seed drill, and the third row to the pesticide applicator, but they will not change after setting.

[0170] S32, according to the utilization rate of each type of agricultural machinery in each target area and the shortage of agricultural machinery in each target area, the initialization position matrix of each snake is iterated T times to obtain the position matrix of each snake after the Tth iteration.

[0171] The utilization rate of each target area for each type of agricultural machinery can be indicated by an agricultural machinery utilization rate matrix. After the host obtains the utilization rate of each type of agricultural machinery in the target area from the client corresponding to each target area, the agricultural machinery utilization rate matrix can be generated. Each row of the agricultural machinery utilization rate matrix contains M elements, and each column contains N elements. The element in the i-th row and j-th column of the agricultural machinery utilization rate matrix is ​​used to indicate the utilization rate of the i-th target area for the j-th type of agricultural machinery, i is greater than or equal to 1 and less than or equal to M, and j is greater than or equal to 1 and less than or equal to N. M is the number of target areas, and N is the number of categories of agricultural machinery.

[0172] It should be noted that, whether it is the initial position matrix or the position matrix obtained after any iterative processing, all elements in any column of the position matrix should be 1. This is because any column in the position matrix represents the weight coefficient of each category of agricultural machinery in the corresponding target area, and the weight coefficient of all categories of agricultural machinery should be 1, otherwise the solution does not conform to the actual situation and needs to be processed.

[0173]

[0174] With position matrix P i For example, it can be seen that the sum of all elements in each column is 1. In some cases, after iterative processing, there are cases where all elements of some columns in the position matrix are not 1. At this time, relevant processing can be performed. For example, calculate the sum of all elements in the column, calculate the ratio of the sum of all elements in the column to 1, and then scale proportionally, so that the sum of all elements in the column can be guaranteed to be 1. In other cases, there may be cases where some elements in the position matrix are negative numbers, which is also not in line with the actual situation, because the weight coefficient should be greater than 0 or equal to 0. For the case of negative numbers, certain methods can be used to process them, such as adding a numerical value to all elements in the column to ensure that all elements in the column are non-negative numbers, and then determine whether the sum of all elements in the column is 1 when the number is added. If not, proportional scaling can be performed. Finally, it is necessary to ensure that all elements in any column are non-negative numbers and the sum of all elements in any column is 1.

[0175] The number of rows in the agricultural machinery utilization rate matrix is ​​the same as the number of rows in the position matrix, and the number of columns in the agricultural machinery utilization rate matrix is ​​also the same as the number of columns in the position matrix. Each column in the agricultural machinery utilization rate matrix corresponds to a target area, and the order of columns corresponding to each target area is the same as the order of columns in the position matrix, that is, if the first column in the position matrix corresponds to the agricultural machinery dispatch in the target area, then the first column in the agricultural machinery utilization rate matrix also corresponds to the agricultural machinery dispatch in the target area, and the same applies to other columns. Each row in the agricultural machinery utilization rate matrix corresponds to an agricultural machinery category, and the order of rows corresponding to each agricultural machinery category is the same as the order of rows in the position matrix, that is, if the second column in the position matrix corresponds to the pesticide applicator, then the second column in the agricultural machinery utilization rate matrix corresponds to the pesticide applicator, and the same applies to other columns.

[0176] Taking a total of 6 target areas (target area agricultural machinery scheduling-target area F) and three agricultural machinery categories (seeder, pesticide applicator, and fertilizer applicator) as an example, a possible agricultural machinery utilization matrix Z value is taken as follows:

[0177]

[0178] The 2nd row and 5th column of the agricultural machinery utilization matrix Z means that the utilization rate of the target area E for the pesticide applicator is 0.78. The same is true for other elements, which will not be repeated here.

[0179] The shortage vector includes M elements. Any i-th element in the shortage vector is used to indicate the shortage of agricultural machinery in the i-th target area, where i is greater than or equal to 1 and less than or equal to M. That is, the number of elements contained in the shortage vector is equal to the number of target areas, that is, each target area has a shortage value, and the arrangement order of the shortage values ​​of each target area in the shortage vector is the same as the arrangement order of the columns corresponding to each target area in the position matrix, that is, if the first column in the position matrix corresponds to the agricultural machinery scheduling of the target area, then the first elements in the shortage vector correspond to the shortage value of the agricultural machinery scheduling of the target area. Still taking a total of 6 target areas (target area agricultural machinery scheduling-target area F in sequence) as an example, a possible value of the shortage vector λ is as follows:

[0180] λ=[0.12 0.45 0.78 0.23 0.56 0.89] (3)

[0181] The second element of the shortage vector λ is 0.45, which means that the shortage value of the target area B is 0.45. The other elements are similar and will not be described here.

[0182] After obtaining the agricultural machinery utilization rate matrix and the agricultural machinery shortage situation vector, the initialization position matrix of each snake can be iteratively processed. Specifically, the target position matrix after the t-th iteration is determined in the position matrix of each snake after the t-th iteration according to the agricultural machinery utilization rate matrix and the agricultural machinery shortage situation vector, and then the position matrix of each snake after the t-th iteration is iteratively processed according to the target position matrix after the t-th iteration, and the position matrix of each snake after the t+1th iteration is obtained, where t is 0, 1, 2, ····, T-1, and the position matrix of each snake after the 0th iteration is the initialization position matrix of each snake.

[0183] For any t+1th iteration process, firstly, according to the agricultural machinery utilization rate and shortage vector, the benefit value corresponding to the position matrix of each snake after the tth iteration is obtained. The calculation formula of the benefit value is as follows:

[0184] fitness=sum(P i ×Z×λ Τ ) (4)

[0185] Among them, P i is the position matrix of the i-th snake, Z is the agricultural machinery utilization matrix, λ is the shortage vector, λ Τ is the transposed matrix of the shortage vector λ, and fitness is the position matrix P of the i-th snake i The benefit value of , sum is the summation function.

[0186] After the position matrix of each snake after the tth iteration is determined, the benefit value corresponding to the position matrix of each snake after the tth iteration can be obtained according to formula (4).

[0187] After obtaining the benefit values ​​corresponding to the position matrices of each snake after the tth iteration, the target position matrix after the tth iteration can be determined in the position matrices of each snake after the tth iteration according to the benefit values. Since the position matrix of each snake indicates an agricultural machinery allocation scheme, according to the benefit values ​​corresponding to the position matrices of each snake after the tth iteration, the position matrix with the highest benefit value can be determined as the target position matrix after the tth iteration.

[0188] After determining the target position matrix after the tth iteration, the t+1th iteration can be performed. Figure 4 The process is described in detail.

[0189] Figure 4 A flowchart of iterative processing provided by an embodiment of the present invention is shown in FIG. Figure 4 As shown, including:

[0190] S41, obtaining the control variable corresponding to the t-th iteration, the control variable corresponding to the t-th iteration is used to control the influence of food and temperature on each snake in the next step, and is used to control the snakes to fight and mate.

[0191] Specifically, first obtain the first preset parameter c1, then obtain the control variable Q according to the preset parameter, and then obtain the control variable Temp according to the number of iterations.

[0192]

[0193] Temp and Q are the control variables corresponding to the tth iteration, and c1 is the first preset parameter. In formula (5), c1 is a preset parameter and remains unchanged; t is the current tth iteration; T is the maximum number of iterations, which also remains unchanged. In formulas (5) and (6), t changes with the number of iterations, so Q and Temp corresponding to different numbers of iterations are also different. In each iteration process, Q and Temp corresponding to the iteration process need to be calculated based on formulas (5) and (6).

[0194] S42, iteratively processing the position matrix of each snake after the t-th iteration according to the control variable corresponding to the t-th iteration and the target position matrix after the t-th iteration, to obtain the position matrix of each snake after the t+1-th iteration.

[0195] After obtaining the control variables corresponding to the t-th iteration, iterative processing can be performed according to the control variables corresponding to the t-th iteration and the target position matrix after the t-th iteration to obtain the position matrix of each snake after the t+1-th iteration. The specific calculation formula is as follows:

[0196] At the t+1 iteration, if Q<0.25, the position matrices of the ith male and female snakes satisfy:

[0197]

[0198] Among them, X i,m X is the individual position of male snake; i,f X is the individual position of female snake; rand,m is the position of a randomly selected male snake; X rand,f is the position of a randomly selected female snake; rand is a random number between [0, 1]; f rand,m X is the position of the randomly selected male snake individual rand,m Return value; f i,m X is the position of the male snake i,m Return value; f rand,f X is the position of the randomly selected female snake rand,f Return value; f i,fX is the position of the female snake i,f Profit value; c2 is the second preset parameter. max is the upper boundary of the snake in the position matrix; X min is the lower boundary of the snake in the position matrix.

[0199] At the t+1 iteration, if Q>0.25 and Temp>0.6, the snake position matrix satisfies:

[0200] X i,j (t+1)=X food ±c3×Temp×rand×(X food -X i,j (t)) (9)

[0201] Among them, X i,j is the individual position; X food is the current optimal profit; c3 is the third preset parameter.

[0202] At the t+1 iteration, if Q>0.25 and Temp<0.6, the snake will randomly enter the fighting state or the mating state. When entering the fighting state, the snake's position matrix satisfies:

[0203]

[0204] Among them, X i,m is the position of the ith male snake; X best,f X is the best position for female snakes; i,f is the position of the ith female individual; X best,m is the best position for male individuals; f best,f is the best benefit value among female snakes; f best,m is the best benefit value among male snakes; f i is the current revenue value.

[0205] When entering the mating state, the snake's position matrix satisfies:

[0206]

[0207] Among them, X i,m is the position of the ith male snake; X i,f is the position of the ith female snake; f i,m is the profit value of the ith male individual position; f i,f is the profit value of the ith female individual position.

[0208] Based on the above four situations, the position matrix of the i-th snake after the t+1th iteration can be obtained by using equations (7) to (13), thereby finally obtaining the position matrix of the snake after the t+1th iteration.

[0209] In the above embodiment, the process of obtaining the position matrix of each snake after the current iteration based on the position matrix of each snake after the previous iteration in any iteration is introduced. The maximum number of iterations is T. After T iterations, the position matrix of each snake after the Tth iteration can be obtained.

[0210] S33, obtaining a target allocation matrix according to the snake position matrix after the Tth iteration.

[0211] After obtaining the position matrix of the snakes after the Tth iteration, the benefit value corresponding to the position matrix of each snake after the Tth iteration can be calculated based on the above formula (4), and then the position matrix of the best benefit value is determined as the target allocation matrix. The method of calculating the benefit value can be referred to the above embodiment and will not be repeated here.

[0212] In the above embodiments, Figure 3 and Figure 4 The process of obtaining the target allocation matrix is ​​introduced below. Figure 5 Provide an overview of the process. Figure 5 A schematic diagram of a process for obtaining a target allocation matrix provided by an embodiment of the present invention is shown in FIG. Figure 5 As shown, including:

[0213] S51, initializing the position matrix of the S snakes according to the number of target areas and the types of agricultural machinery.

[0214] S52, calculating the benefit value of each initialization position matrix according to the initialization position matrix, and recording the target position matrix with the largest benefit value.

[0215] S53, updating the position matrix of each snake according to the target position matrix.

[0216] S54, update control variables Q and Temp.

[0217] S55, calculating the benefit value corresponding to the position matrix of each snake.

[0218] S56, determine whether the number of iterations is equal to the maximum number of iterations T, if so, execute S57, if not, execute S53.

[0219] S57, output the optimal target allocation matrix.

[0220] After the target allocation matrix is ​​obtained, the allocation quantity of each target area for each category of agricultural machinery can be determined based on the demand for each category of agricultural machinery in each target area and the target allocation matrix.

[0221] When there are sufficient agricultural machinery of all kinds, for any target area, the proportion of the allocation of agricultural machinery of each category allocated to the target area can be guaranteed to meet the proportion corresponding to the target allocation matrix under the premise of satisfying the demand for agricultural machinery of each category. That is, the ratio of the allocation of agricultural machinery of a category to that of agricultural machinery of a category not allocated to the target area is indicated by the allocation vector corresponding to the target area in the target allocation matrix, and the allocation of agricultural machinery of any category in the target area is greater than or equal to the demand of the target area for agricultural machinery of that category.

[0222] When the number of agricultural machinery of each category is insufficient, the weight ratio of each target area to each category of agricultural machinery can be determined according to the target allocation matrix.

[0223] by For example, the matrix is ​​the target allocation matrix, where the agricultural machinery category corresponding to the first row is the seed drill, then the weight ratio of the target area agricultural machinery scheduling - target area F for the seed drill is 0.25:0.25:0.48:0.56:0.20:0.27. For other categories of agricultural machinery, the weight ratio is calculated in the same way.

[0224] Then, according to the weight ratio of each target area to each type of agricultural machinery and the demand for each type of agricultural machinery in each target area, the allocation amount of each target area to each type of agricultural machinery is determined. For example, after the weight ratio of the seed drill is determined, the allocation amount of the seed drill to each target area can be determined according to the total number of seed drills and the weight ratio of the seed drill. According to the above method, the allocation amount of each type of agricultural machinery allocated to each target area can be obtained.

[0225] The following is a detailed description of the parameter settings and simulation results of the computer simulation experiment of the embodiment of the present invention. The target area is set to 6 farms, and the agricultural machinery categories include seeders, pesticide applicators, fertilizer applicators, and harvesters. The farm agricultural machinery dispatch center can use the algorithm in the embodiment of the present invention to obtain the dispatch plan and run it. The number of snakes set S = 30, and the maximum number of iterations T = 200; the number of individuals in the genetic algorithm population for comparison is set to 30, and the maximum number of iterations is 200.

[0226] Figure 6 A comparative schematic diagram of the agricultural machinery scheduling scheme provided by an embodiment of the present invention, such as Figure 6 As shown, Figure 6The solid line in the middle is a benefit value simulation curve calculated by the agricultural machinery scheduling scheme of the embodiment of the present invention. During the 200 iterations, it can be observed from the simulation curve that the economic benefit of the comprehensive agricultural machinery scheduling scheme of this scheme is significantly higher than the economic benefit value of the comprehensive agricultural machinery scheduling scheme obtained by using the genetic algorithm, indicating that the scheduling scheme provided by the present invention can significantly improve the scheduling quality of the farm for comprehensive agricultural machinery scheduling. At the same time, it can be seen from the figure that the efficiency of this scheme is much higher than that of the genetic algorithm, and it gradually converges after 55 iterations, while the genetic algorithm does not reach horizontal convergence during the entire 200 iterations, which is not conducive to actual application scenarios.

[0227] To sum up, the solution of the embodiment of the present invention is to solve the problem of comprehensive agricultural machinery scheduling being difficult to achieve reasonable scheduling of comprehensive agricultural machinery due to deep coupling or conflict in comprehensive agricultural machinery scheduling. Through snake optimization processing, when facing large-scale agricultural machinery scheduling problems, the agricultural machinery scheduling can be solved, which can avoid falling into local optimal solutions, meet the needs of various target areas for various types of agricultural machinery, improve the comprehensive utilization rate of agricultural machinery, and achieve reasonable scheduling of agricultural machinery.

[0228] Figure 7 A schematic diagram of the structure of the integrated agricultural machinery dispatching device provided by an embodiment of the present invention is shown in FIG. Figure 7 As shown, the comprehensive agricultural machinery scheduling device includes:

[0229] A receiving module, used for receiving the demand for each type of agricultural machinery in each target area from the clients corresponding to each target area;

[0230] A processing module, used for performing snake optimization processing based on the utilization rate of each target area for each category of agricultural machinery and the shortage of agricultural machinery in each target area, and obtaining a target allocation matrix, wherein the target allocation matrix includes allocation vectors corresponding to each target area, and the allocation vector corresponding to any target area is used to indicate the weight of each category of agricultural machinery corresponding to the target area;

[0231] The determination module is used to determine the allocation quantity of each target area for each category of agricultural machinery according to the demand quantity of each target area for each category of agricultural machinery and the target allocation matrix.

[0232] In a possible implementation manner, the processing module is specifically applied to

[0233] Obtaining initialization parameters, the initialization parameters include the maximum number of iterations T, the number of snakes S, and the initialization position matrix of each snake, any position matrix contains M×N elements, M is the number of target areas, and N is the number of agricultural machinery categories. Both M and N are integers greater than 1;

[0234] According to the utilization rate of each target area for each type of agricultural machinery and the shortage of agricultural machinery in each target area, the initialization position matrix of each snake is iterated T times to obtain the position matrix of each snake after the Tth iteration;

[0235] The target allocation matrix is ​​obtained according to the position matrix of each snake after the Tth iteration.

[0236] In a possible implementation manner, the processing module is specifically applied to:

[0237] Determine the target position matrix after the t-th iteration in the position matrix of each of the snakes after the t-th iteration according to the agricultural machinery utilization matrix and the shortage vector;

[0238] According to the target position matrix after the t-th iteration, iteratively process the position matrix of each snake after the t-th iteration to obtain the position matrix of each snake after the t+1-th iteration;

[0239] The t is 0, 1, 2, ..., T-1 in sequence, and the position matrix of each snake after the 0th iteration is the initialization position matrix of the position matrix of each snake;

[0240] The agricultural machinery utilization rate matrix includes M×N elements, and the element in the mth row and nth column of the agricultural machinery utilization rate matrix is ​​used to indicate the utilization rate of the mth target area for the nth category of agricultural machinery, wherein m is greater than or equal to 1 and less than or equal to M, and n is greater than or equal to 1 and less than or equal to N;

[0241] The agricultural machinery shortage vector contains M elements, and any i-th element in the shortage vector is used to indicate the agricultural machinery shortage situation in the i-th target area, where i is greater than or equal to 1 and less than or equal to M.

[0242] In a possible implementation manner, the processing module is specifically applied to:

[0243] The control variable corresponding to the t-th iteration is obtained, and the control variable corresponding to the t-th iteration is used to control the influence of food and temperature on each of the snakes in the next step, and to control the fighting and mating of each of the snakes.

[0244] According to the control variables corresponding to the t-th iteration and the target position matrix after the t-th iteration, the position matrix of each snake after the t-th iteration is iteratively processed to obtain the position matrix of each snake after the t+1-th iteration.

[0245] In a possible implementation manner, the processing module is specifically applied to:

[0246] The control variable corresponding to the t-th iteration is obtained, and the control variable corresponding to the t-th iteration is used to control the influence of food and temperature on each of the snakes in the next step, and to control the fighting and mating of each of the snakes.

[0247] According to the control variables corresponding to the t-th iteration and the target position matrix after the t-th iteration, the position matrix of each snake after the t-th iteration is iteratively processed to obtain the position matrix of each snake after the t+1-th iteration.

[0248] In a possible implementation manner, the processing module is specifically applied to:

[0249] Obtaining a first preset parameter;

[0250] Obtaining a control variable corresponding to the tth iteration according to the first preset parameter and the current iteration number t;

[0251] in, The Q and Temp are control variables corresponding to the t-th iteration, and the c1 is a first preset parameter.

[0252] In one possible implementation, at the t+1 iteration, if Q<0.25, the position matrices of the i-th male snake and the female snake satisfy:

[0253]

[0254]

[0255] Among them, X i,m X is the individual position of male snake; i,f X is the individual position of female snake; rand,m is the position of a randomly selected male snake; X rand,f is the position of a randomly selected female snake; rand is a random number between [0, 1]; f rand,m X is the position of the randomly selected male snake individual rand,m Return value; f i,m X is the position of the male snake i,m Return value; f rand,f X is the position of the randomly selected female snake rand,f Return value; f i,f X is the position of the female snake i,f Profit value; c2 is the second preset parameter. max is the upper boundary of the snake in the position matrix; X min is the lower boundary of the snake in the position matrix.

[0256] At the t+1 iteration, if Q>0.25 and Temp>0.6, the snake's position matrix satisfies:

[0257] X i,j (t+1)=X food ±c3×Temp×rand×(X food -X i,j (t))

[0258] Among them, X i,j is the individual position; X food is the current optimal profit; c3 is the third preset parameter.

[0259] At the t+1 iteration, if Q>0.25 and Temp<0.6, the snake will randomly enter the fighting state or the mating state. When entering the fighting state, the snake's position matrix satisfies:

[0260]

[0261] Among them, X i,m is the position of the ith male snake; X best,f X is the best position for female snakes; i,f is the position of the ith female individual; X best,m is the best position for male individuals; f best,f is the best benefit value among female snakes; f best,m is the best benefit value among male snakes; f i is the current revenue value.

[0262] When entering the mating state, the snake's position matrix satisfies:

[0263]

[0264] Among them, X i,m is the position of the ith male snake; X i,f is the position of the ith female snake; f i,m is the profit value of the ith male individual position; f i,f is the profit value of the i-th female individual position.

[0265] In a possible implementation manner, the determining module is specifically applied to:

[0266] Determine the weight ratio of each target area to each category of agricultural machinery according to the target allocation matrix;

[0267] The allocation quantity of each target area for each category of agricultural machinery is determined according to the weight ratio of each target area to each category of agricultural machinery and the demand of each target area for each category of agricultural machinery.

[0268] The comprehensive agricultural machinery scheduling device provided in the embodiment of the present invention is used to execute the above-mentioned embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be repeated here.

[0269] Figure 8 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 8 As shown, the electronic device may include: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus. The processor may call the logic instructions in the memory to execute the comprehensive agricultural machinery scheduling method, which includes: receiving the demand for each category of agricultural machinery in each target area from the client corresponding to each target area; performing snake optimization processing based on the utilization rate of each target area for each category of agricultural machinery and the shortage of agricultural machinery in each target area to obtain a target allocation matrix, wherein the target allocation matrix includes the allocation vector corresponding to each target area, and the allocation vector corresponding to any target area is used to indicate the weight of each category of agricultural machinery corresponding to the target area; according to the demand for each category of agricultural machinery in the target area and the target allocation matrix, determining the allocation amount of each category of agricultural machinery in each target area.

[0270] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various storage media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), or an optical disk.

[0271] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the comprehensive agricultural machinery scheduling method provided by the above-mentioned methods, which includes: receiving the demand for each category of agricultural machinery in each target area from the client corresponding to each target area; performing snake optimization processing based on the utilization rate of each target area for each category of agricultural machinery and the shortage of agricultural machinery in each target area to obtain a target allocation matrix, wherein the target allocation matrix includes allocation vectors corresponding to each target area, and an arbitrary target allocation matrix, wherein the target allocation matrix includes allocation vectors corresponding to each target area, and the allocation vectors corresponding to any target area are used to indicate the weights of each category of agricultural machinery corresponding to the target area; determining the allocation quantity of each target area for each category of agricultural machinery according to the demand for each category of agricultural machinery in each target area and the target allocation matrix.

[0272] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the comprehensive agricultural machinery scheduling method provided by the above-mentioned methods, the method comprising: receiving the demand for each category of agricultural machinery in each target area from a client corresponding to each target area; performing snake optimization processing based on the utilization rate of each target area for each category of agricultural machinery and the shortage of agricultural machinery in each target area to obtain a target allocation matrix, wherein the target allocation matrix includes allocation vectors corresponding to each target area, and the allocation vector corresponding to any target area is used to indicate the weight of each category of agricultural machinery corresponding to the target area; determining the allocation quantity of each category of agricultural machinery in each target area according to the demand for each category of agricultural machinery in each target area and the target allocation matrix.

[0273] The device examples described above are merely illustrative, wherein the units described as separated and not illustrated may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0274] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on the above understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM, RAM, optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiment.

[0275] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A comprehensive agricultural machinery scheduling method, characterized in that: The following steps are involved: Obtain the demand for agricultural machinery in each target area, and obtain the agricultural machinery utilization rate and agricultural machinery shortage vector in each target area; Performing snake optimization processing on the agricultural machinery utilization rate and agricultural machinery shortage situation vectors to obtain a target allocation matrix; The allocation quantity of each target area for each type of machine model is determined based on the demand quantity of agricultural machinery in each target area and the target allocation matrix.

2. The integrated agricultural machinery scheduling method according to claim 1, characterized in that: The process of performing snake optimization processing on the agricultural machinery utilization rate and the agricultural machinery shortage situation to obtain the target allocation matrix includes: Get the initialization parameters and the initialization position matrix of the snake; Based on the agricultural machinery utilization rate and agricultural machinery shortage situation of each target area, the initialization position matrix of the snake is iterated T times to obtain the position matrix of each snake after the Tth iteration; The target allocation matrix is ​​obtained based on the position matrix of each snake after the Tth iteration.

3. The integrated agricultural machinery dispatching method according to claim 2, characterized in that: The process of obtaining the position matrix of each snake after the Tth iteration also includes: Determine the target position matrix after the t-th iteration based on the position matrices of each snake after the t-th iteration; According to the target position matrix after the t-th iteration, iteratively process the position matrix of each snake after the t-th iteration to obtain the position matrix of each snake after the t+1-th iteration; Among them, {t|t=0,1,2,…,T-1}.

4. The integrated agricultural machinery scheduling method according to claim 2, characterized in that: The process of determining the target position matrix after the t-th iteration based on the position matrix of each snake after the t-th iteration includes: Obtaining the benefit value corresponding to the snake position matrix after the tth iteration for the agricultural machinery utilization rate and agricultural machinery shortage situation vector; Determining the target allocation matrix after the t-th iteration based on the benefit value and the snake position matrix after the t-th iteration; The target allocation matrix includes allocation vectors corresponding to each of the target areas, and the allocation vector corresponding to any target area is used to indicate the weight of each category of agricultural machinery corresponding to the target area; The initialization position matrix of the snake contains M×N elements, where M is the number of the target areas, and N is the number of categories of agricultural machinery, and both M and N are integers greater than 1.

5. The integrated agricultural machinery dispatching method according to claim 3, characterized in that: According to the target position matrix after the t-th iteration, the position matrix of each snake after the t-th iteration is iteratively processed to obtain the position matrix of each snake after the t+1-th iteration, which includes: Obtaining a control variable corresponding to the t-th iteration, wherein the control variable corresponding to the t-th iteration is used to control the influence of food and temperature on each snake in the next step, and is used to control the fighting and mating of each snake; According to the control variables corresponding to the t-th iteration and the target position matrix after the t-th iteration, the position matrix of each snake after the t-th iteration is iteratively processed to obtain the position matrix of each snake after the t+1-th iteration.

6. The integrated agricultural machinery dispatching method according to claim 5, characterized in that: The process of obtaining the control variable corresponding to the t-th iteration includes: Obtaining a first preset parameter; Obtaining a control variable corresponding to the tth iteration according to the first preset parameter and the current iteration number t; The expression of the control variable corresponding to the t-th iteration is: Among them, Q and Temp are control variables corresponding to the t-th iteration, and c1 is the first preset parameter.

7. The integrated agricultural machinery dispatching method according to claim 6, characterized in that: At the t+1 iteration, if Q<0.25, the position matrices of the i-th male and female snakes satisfy: Among them, X i,m X is the individual position of male snake; i,f X is the individual position of female snake; rand,m is the position of a randomly selected male snake; X rand,f is the position of a randomly selected female snake; rand is a random number between [0, 1]; f rand,m X is the position of the randomly selected male snake individual rand,m Return value; f i,m X is the position of the male snake i,m Return value; f rand,f X is the position of the randomly selected female snake rand,f Return value; f i,f X is the position of the female snake i,f Profit value; c2 is the second preset parameter; X max is the upper boundary of the snake in the position matrix; X min is the lower boundary of the snake in the position matrix; At the t+1 iteration, if Q>0.25 and Temp>0.6, the snake position matrix satisfies: X i,j (t+1)=X food ±c3×Temp×rand×(X food -X i,j (t)) Among them, X i,j is the individual position; X food is the current optimal benefit; c3 is the third preset parameter; At the t+1 iteration, if Q>0.25 and Temp<0.6, the snake will randomly enter the fighting state or the mating state. When entering the fighting state, the snake's position matrix satisfies: Among them, X i,m is the position of the ith male snake; X best,f X is the best position for female snakes; i,f is the position of the ith female individual; X best,m is the best position for male individuals; f best,f is the best benefit value among female snakes; f best,m is the best benefit value among male snakes; f i is the current revenue value; When entering the mating state, the snake's position matrix satisfies: Among them, X i,m is the position of the ith male snake; X i,f is the position of the ith female snake; f i,m is the profit value of the ith male individual position; f i,f is the profit value of the i-th female individual position.

8. The integrated agricultural machinery dispatching method according to claim 1, characterized in that: The process of determining the allocation amount of each target area for each type of machine model based on the agricultural machinery demand of each target area and the target allocation matrix includes: Determine the weight ratio of each target area to each category of agricultural machinery according to the target allocation matrix; The allocation quantity of each target area for each category of agricultural machinery is determined according to the weight ratio of each target area to each category of agricultural machinery and the demand of each target area for each category of agricultural machinery.

9. A comprehensive agricultural machinery dispatching device, characterized in that: include: A receiving module, used for receiving the demand for each type of agricultural machinery in each target area from the clients corresponding to each target area; A processing module, used for performing snake optimization processing based on the utilization rate of each target area for each type of agricultural machinery and the shortage of agricultural machinery in each target area to obtain a target allocation matrix; The determination module is used to determine the allocation quantity of each target area for each category of agricultural machinery according to the demand quantity of each target area for each category of agricultural machinery and the target allocation matrix.

10. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the integrated agricultural machinery scheduling method as described in any one of claims 1 to 8 is implemented.

Citation Information

Cited By

  • Agricultural digital intelligence resource configuration management system and method based on dynamic prediction

    CN121581322A